| summary.monte {fungible} | R Documentation |
Summary Method for an Object of Class Monte
Description
summary method for class “monte"
Usage
## S3 method for class 'monte'
summary(
object,
digits = 3,
compute.validities = FALSE,
Total.stats = TRUE,
...
)
Arguments
object |
An object of class |
digits |
Number of digits to print. Default = 3. |
compute.validities |
Logical: If TRUE then the program will calculate the indicator validities (eta^2) for the generated data. |
Total.stats |
Logical: If TRUE then the program will return the following statistics for the total sample: (1) indicator correlation matrix, (2) indicator skewness, (3) indicator kurtosis. |
... |
Optional arguments. |
Value
Various descriptive statistics will be computed within groups including"
- clus.size
Number of objects within each group.
- centroids
Group centroids.
- var.matrix
Within group variances.
- cor.list
Expected within group correlations.
- obs.cor
Observed within group correlations.
- skew.list
Expected within group indicator skewness values.
- obs.skew
Observed within group indicator skewness values.
- kurt.list
Expected within group indicator kurtosis values.
- obs.kurt
Observed within group indicator kurtosis values.
- validities
Observed indicator validities.
- Total.cor
Total sample correlation matrix.
- Total.skew
Total sample indicator skewness.
- Total.kurt
Total sample indicator kurtosis.
Examples
## set up a 'monte' run for the Fisher iris data
sk.lst <- list(c(0.120, 0.041, 0.106, 1.254), #
c(0.105, -0.363, -0.607, -0.031),
c(0.118, 0.366, 0.549, -0.129) )
kt.lst <- list(c(-0.253, 0.955, 1.022, 1.719),
c(-0.533,-0.366, 0.048, -0.410),
c( 0.033, 0.706, -0.154, -0.602))
cormat <- lapply(split(iris[,1:4],iris[,5]), cor)
my.iris <- monte(seed = 123, nvar = 4, nclus = 3, cor.list = cormat,
clus.size = c(50, 50, 50),
eta2 = c(0.619, 0.401, 0.941, 0.929),
random.cor = FALSE,
skew.list = sk.lst, kurt.list = kt.lst,
secor = .3,
compactness = c(1, 1, 1),
sortMeans = TRUE)
summary(my.iris)